Search

Automatic detection and segmentation of the common carotid artery in transverse ultrasound (US) images of the thyroid gland play a vital role in the success of US guided intervention procedures. We propose in this paper a novel method to accurately detect, segment and track the carotid in 2D and 2D+t US images of the thyroid gland using concepts based on tissue echogenicity and ultrasound image formation. We first segment the hypoechoic anatomical regions of interest using local phase and energy in the input image. We then make use of a Hessian based blob like analysis to detect the carotid within the segmented hypoechoic regions. The carotid artery is segmented by making use of least squares ellipse fit for the edge points around the detected carotid candidate. Experiments performed on a multivendor dataset of 41 images show that the proposed algorithm can segment the carotid artery with high sensitivity (99.6 ±m 0.2%) and specificity (92.9 ±m 0.1%). Further experiments on a public database containing 971 images of the carotid artery showed that the proposed algorithm can achieve a detection accuracy of 95.2% with a 2% increase in performance when compared to the state-of-the-art method.

This paper presents a probabilistic method for active localization of needles and targets in robotic image guided interventions. Specifically, an active localization scenario where the system directly controls the imaging system to actively localize the needle and target locations using intra-operative medical imaging (e.g., computerized tomography and ultrasound imaging) is explored. In the proposed method, the active localization problem is posed as an information maximization problem, where the beliefs for the needle and target states are represented and estimated using particle filters. The proposed method is also validated using a simulation study.

The fusion of ultrasound (US) with CT plays a vital role in clinical diagnosis and image guided intervention. A registration framework between preoperative CT and tracked 2D intraoperative US is proposed here for hepatic intervention. After a landmark based registration method is carried out to get the initial registration, a simulation model of US from CT scan is developed to simulate the major US effects. The innovation is incorporating spatial and intensity scale information in a new similarity metric, which is to register the selected US image containing crucial anatomical features and the simulated US from CT. Experiments of 5 patients illustrate that our registration method achieved an average FRE and TRE of 3.81 ± 1.16 mm and 4.13 ± 1.27 mm.